Before you govern it, you can see it.
Observability is not bolted on after the fact. It is built into the engine: an immutable audit trail, compliance at the point of decision, memory that persists, and agent-level governance for the AI acting on your pipeline.
Four guarantees, built into the engine.
Immutable audit trail
Every decision the AI makes is written to an immutable audit trail. You can reconstruct any funnel: what was tried, what was rejected, why, and who approved it. Per-stage logging across the full discovery funnel — reproducible, reconstructable, exportable. It is the first question every enterprise buyer asks, and it cannot be retrofitted without paying for provenance twice.
FAVES V4 compliance
1,585 SMARTS across 8 jurisdictions, run inline at the point of decision rather than as a terminal gate that kills late-stage candidates. Compliance is a property the engine checks while it reasons, not a report it generates afterward.
Cross-run memory
Funnel context persists across sessions. The engine remembers what prior runs learned and carries it into the next — so a program compounds knowledge instead of restarting it.
Agent governance
RFC 8693 token exchange, per-agent key scoping, and agent-level audit on Enterprise. As AI agents act on your pipeline, each one is identified, scoped, and logged.
The gaps we keep in plain sight.
Stating what is unfinished is part of the audit. These do not move until the work does.
SOC 2
Not started. We will say so until it is.
Formal validation
Not started. Published benchmarks stand in for it today, openly.
Oncology & CNS prediction
NovoExpert-3 is competent on cardiovascular and GI, and not yet validated on oncology, CNS, or infectious indications. We mark the boundary rather than blur it.
Audit it before you adopt it.
Design a deployment with the audit trail, compliance, and agent governance your review process requires.